Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency and conditions of human behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ФедеÑĢаÑĨии
    -0.16
     Raq
    -0.15
    uzzi
    -0.15
    amet
    -0.15
    rve
    -0.14
    aq
    -0.14
    jeme
    -0.14
    lsen
    -0.14
    lap
    -0.14
    ovie
    -0.13
    POSITIVE LOGITS
    kins
    0.15
    636
    0.14
    /Runtime
    0.13
    bot
    0.13
     tal
    0.13
    763
    0.13
     Bor
    0.13
     tunnel
    0.13
    646
    0.13
     sacr
    0.13
    Act Density 0.140%

    No Known Activations